Land surface water automatic identification method based on Sentinel-1 microwave satellite image
A satellite image and automatic recognition technology, applied in the field of remote sensing target recognition, can solve the problems of abnormal imaging, increasing the difficulty of identifying land surface water in abnormal areas, and the difficulty of obtaining land surface information by optical satellites, so as to achieve objective recognition results and eliminate image abnormalities Imaging problems, the effect of improving recognition accuracy
Active Publication Date: 2020-05-05
HENAN UNIVERSITY
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, there are still some shortcomings in the current technical methods for extracting land surface water
It is generally believed that the Modified Normalized Difference Water Index (MNDWI) constructed from optical satellite images can accurately identify land surface water, but due to the influence of clouds and fog, especially in rainy areas, it is difficult for optical satellites to obtain information, thus exposing the drawbacks of the optical remote sensing method
Sentinel-1 microwave satellite images are susceptible to interference from ships and cause imaging anomalies, causing land surface water information within a certain range around the ship to appear as non-land surface water characteristics, thus increasing the difficulty of identifying land surface water in abnormal areas
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0041] Sentinel-1 satellite images are susceptible to interference from ships and cause imaging anomalies. The normal backscattering coefficient of water in Sentinel-1 satellite images is generally less than -15dB, which appears dark in the image. However, the ship will cause an abnormal increase in the backscattering coefficient of its surrounding area, which is highlighted in the Sentinel-1 satellite image, such as image 3 As show...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an automatic land surface water identification method based on a Sentinel-1 microwave satellite image, and the method comprises the steps: firstly, obtaining an SSWI image through the Sentinel-1 microwave satellite image; secondly, processing the SSWI image by using the constructed SSWI land surface water identification model to obtain a land surface water-non-land surface water binary image; then, obtaining land surface water-non-land surface water binary images of a plurality of historical days, calculating the probability that the land surface water is observed by theSentinel-1 microwave satellite, and obtaining a positive mask image according to the probability; correcting the land surface water-non-land surface water binary image by using a quadratic discrimination model; and finally, performing negation operation on the positive mask image, multiplying the positive mask image by the land surface water-non-land surface water binary image, and splicing the positive mask image with the corrected land surface water-non-land surface water binary image to obtain spatial distribution of land surface water. Under the interference background of ships and cloudand rain weather, the land surface water identification precision can be effectively improved, and land surface water automatic identification is realized.
Description
technical field [0001] The invention relates to the technical field of remote sensing target identification, in particular to an automatic identification method of land surface water based on Sentinel-1 microwave satellite images. Background technique [0002] As an important form of water resources storage, land surface water is not only the main source of water for production and living in human society, but also an important element of natural ecosystems, with extremely important social and economic value and ecological service functions. Affected by the combined effects of precipitation recharge, evapotranspiration, and human water use, the land surface water area has significant fluctuation characteristics in a short period of time. Accurate acquisition of land surface water area and distribution information has important practical significance and scientific value for water resources development and management, ecosystem research and other fields. [0003] Satellite r...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/194G06V20/47G06V20/13
Inventor 田海峰秦耀辰张丽君王家辉
Owner HENAN UNIVERSITY